Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    it's followed by phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oviruses
    0.44
     endomet
    0.43
    𝒟
    0.43
     ℝ
    0.42
    秆
    0.41
     👍
    0.40
     📫
    0.40
     oncologist
    0.40
    変数
    0.40
     léz
    0.39
    POSITIVE LOGITS
     single
    0.39
     ten
    0.39
     circle
    0.38
     protest
    0.37
     sort
    0.36
     transfer
    0.36
     surface
    0.36
     next
    0.35
     </
    0.35
     Ten
    0.35
    Act Density 0.000%

    No Known Activations